So I presume this is the tutorial you've tried? I think you need to replace the float model (where it says "float_model = mobilenet_v2(weights=weights)") by your own floating point trained model, which you can upload to the Colab. Or you could follow the steps on your own machine. Does that answer the question at all, or are you looking for something else? Thanks!...
I have now run the notebook
example_pytorch_post_training_quantization.ipynb
in Google CoLab. This also works so far. But I don't understand where I can place my own model trained with YOLOv8 in it.
Statistics: Posted by therealdavidp — Tue Oct 29, 2024 4:02 pm